Jahaz/Qwen3-tts-0.6b-gguf-for-koboldcpp

Update README.md

Update README.md

Update README.md

Update README.md

MXFP4 wavtokenizer

Update README.md

update mxfp4 for faster speed

Update README.md

better quality than iq4xs in long transcript

Update README.md

Update README.md

Update README.md

Update README.md

Part of tensor be quanted to iq3s.

Update README.md

Update README.md

Update README.md

Smaller tokenizer

Update README.md

Update README.md

Update README.md

qwen3-tts-o.6b-Iq4xs.gguf

Update README.md

requantized qwen3-tts-0.6b-q8_0.gguf

Update README.md

Create README.md

tokenizer file, mixed fp16, fp32 with iq4xs due to block size limit.

initial commit